poethan Goto Github PK

makemeahanzi

Free, open-source Chinese character data

mcmc_tqe

Monte Carlo Modelling of Confidence Intervals in Translation Quality Evaluation (TQE) and Post-Editing Distance (PED) Measurement

mosesdecoder

Moses, the machine translation system

mp-aligner

The MPAligner is a toolkit for cross-lingual term mapping in term tagged documents. The toolkit is specifically designed to address term mapping between European languages. The source code has been released.

mwe-tools

A set of useful tools for use with multiword expression extraction from parallel corpora for Moses statistical machine translation system

mwe4mt

PhD Thesis MWE-MT related tools and sources

mwetoolkit

KWARC's fork of http://sourceforge.net/projects/mwetoolkit/

nematus

Open-Source Neural Machine Translation in Tensorflow

neuralmonkey

An open-source tool for sequence learning in NLP built on TensorFlow.

nlpir

nmt-coverage

Attention-based NMT with a coverage mechanism to indicate whether a source word is translated or not

opennmt

Open-Source Neural Machine Translation in Torch

py-hlepor

Python Bindings to hLEPOR metric

pyactr

Python package for ACT-R cognitive models

python-speech-translate

Python examples for the Speech Translation API

pytorch-pretrained-bert

The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.

qe

Quality Estimation of MT, related codes

rnnsearch

An implementation of attention-based neural machine translation using Pytorch

run_stanfordner

some small codes and documents about running Stanford_NER tagger

segment-mteval

Crowd-sourcing Segment-level MT Evaluations

seq2seq-attn

Sequence-to-sequence model with LSTM encoder/decoders and attention

seqlabel

slides

Presentation slides of projects and papers, MT/NLP/ML/DL

smile-autophrase

stack-lstm-ner

NER system based on stack LSTMs

stopwords

中文常用停用词表（哈工大停用词表、百度停用词表等）

swed_covid_tm

Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Method

tagger

Named Entity Recognition Tool

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

tensorflow-char-rnn

Char-RNN implemented using TensorFlow.